检索结果-内蒙古大学图书馆

An Example of Verification of the Initial data for Designing NPP Information Base 13

学校读者我要写书评

暂无评论

An Example of Verification of the Initial Data for Designing...

13th International Conference Management of Large-Scale System Development, MLSD 2020

作者： Budynkova, Elizaveta Baybulatov, Artur Moscow Aviation Institute Department of Control Systems Informatics and Electric Power Industry Moscow Russia V.A. Trapeznikov Institute of Control Sciences of Ras Ivery Prangishvili Laboratory 31 "distributed Data-Analysis and Control Systems" Moscow Russia

ISBN: (数字)9781728110943

ISBN: (纸本)9781728110943

Nowadays, verification of the initial data for designing the information base of the NPP Automated Process Control System is a guarantee of the correct operation of the NPP Automated Process Control System itself. For this verification, exact and approximate methods are usually applied. Each method provides desirable results for an appropriate problem type. Exact methods are more suitable for solving this problem. The article presents a solution algorithm in terms of checking both the structure and the content of initial data, including a complete parsing of the Kraftwerk Kennzeichen System code with the study of all its sectors. A list of the most common inconsistencies is also provided. © 2020 IEEE.

关键词： Control systems

Enhancing Findability and Searchability of Research data: Metadata Conversion and Registration in Institutional Repositories

学校读者我要写书评

暂无评论

data Science Journal 2024年 23卷

作者： Nosé, Masahito Shinbori, Atsuki Miyoshi, Yoshizumi Hori, Tomoaki Ohira, Tsukasa Hashiba, Junko Naoe, Chizuko Gakiya, Rui Okamoto, Maiko Sagara, Takeshi Aoki, Takaaki Matsubara, Shigeki Takahashi, Ichiro Hayashi, Hidekazu Yamada, Kazunari Minamiyama, Yasuyuki Tanaka, Yoshimasa Abe, Shuji Ueno, Satoru Imajo, Shun Saito, Yasuo Ashikita, Takuya Hori, Yuko Shimizu, Toshiyuki Okamura, Nanako Hirano, Kaoru Bargatze, Lee School of Data Science Nagoya City University Nagoya Japan Institute for Space-Earth Environmental Research Nagoya University Nagoya Japan Nagoya University Library Nagoya Japan Info Proto Co. Ltd Tokyo Japan Information Strategy Office Information and Communications Nagoya University Nagoya Japan Information Technology Center Information and Communications Nagoya University Nagoya Japan Research Center for Open Science and Data Platform National Institute of Informatics Tokyo Japan Polar Environment Data Science Center Research Organization of Information and Systems Tachikawa Japan National Institute of Polar Research Tachikawa Japan Graduate Institute for Advanced Studies SOKENDAI Tachikawa Japan International Research Center for Space and Planetary Environmental Science Kyushu University Fukuoka Japan Astronomical Observatory Graduate School of Science Kyoto University Kyoto Japan Data Analysis Center for Geomagnetism and Space Magnetism Graduate School of Science Kyoto University Kyoto Japan Kyushu University Library Fukuoka Japan Earth Planetary and Space Sciences University of California Los Angeles United States

This paper outlines our practice to enhance the findability and searchability of research data through metadata conversion from the Space Physics Archive Search and Extract (SPASE) schema to a more generic schema, the Japan Consortium for Open Access Repository (JPCOAR) schema, and registration of converted metadata in institutional repositories. Traditionally, earth and space science research data have been organized using the SPASE schema. Although the SPASE schema is comprehensive, its usage has been restricted to highly professional databases, limiting broader accessibility and impeding cross-disciplinary research. We discuss a case study at Nagoya University where 284 metadata records were converted from SPASE to JPCOAR, and illustrate the process and benefits of this conversion. This approach significantly improved the visibility and usability of metadata across various platforms like the Institutional Repositories dataBase (IRDB), the data Catalog Cross-Search System, and Google’s dataset Search, extending access to a wider range of users beyond the highly professional scientific community. This approach also aligns with national policies in Japan on research data management and simplifies metadata handling for researchers. Future direction includes expanding this conversion and registration model to other universities and institutions by leveraging the ubiquity of the SPASE schema in the earth and space science fields. Our practice may be useful in other research fields. This initiative aims to improve the overall findability of research data, to foster cross-disciplinary collaboration, and to enhance the value of research data itself and of creators and managers of the data. © 2024 The Author(s).

关键词： data consistency

A complete description of the dynamics of legal outer-totalistic affine continuous cellular automata

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Wolnik, Barbara Dembowski, Marcin Augustynowicz, Antonii De Baets, Bernard Gdansk University Poland Institute of Mathematics Faculty of Mathematics Physics and Informatics University of Gdańsk Gdańsk80-308 Poland KERMIT Department of Data Analysis and Mathematical Modelling Ghent University Gent9000 Belgium

This paper presents an investigation into the evolution and dynamics of the simplest generalization of binary cellular automata: Affine Continuous Cellular Automata (ACCAs), with [0, 1] as state set and local rules that are affine in each variable. The focus lies on legal outer-totalistic ACCAs, an interesting class of dynamical systems that show some properties that do not occur in the binary case. A unique combination of computer simulations (sometimes quite advanced) and a panoply of analytical methods allow to lay bare the dynamics of each and every one of these cellular automata. The results show that in the class of ACCAs considered, one can observe all types of sensitivity: sensitivity to the change of the number of cells in the grid, sensitivity to slight changes in the parameters of a local rule and sensitivity to the change of a single value in an initial configuration. © 2021, CC BY.

关键词： Cellular automata

Implicit Neural Representation in Medical Imaging: A Comparative Survey

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Molaei, Amirali Aminimehr, Amirhossein Tavakoli, Armin Kazerouni, Amirhossein Azad, Bobby Azad, Reza Merhof, Dorit School of Computer Engineering Iran University of Science and Technology Tehran Iran School of Electrical Engineering Iran University of Science and Technology Tehran Iran South Dakota State University BrookingsSD United States Faculty of Electrical Engineering and Information Technology RWTH Aachen University Aachen Germany Institute of Image Analysis and Computer Vision Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany

Implicit neural representations (INRs) have gained prominence as a powerful paradigm in scene reconstruction and computer graphics, demonstrating remarkable results. By utilizing neural networks to parameterize data through implicit continuous functions, INRs offer several benefits. Recognizing the potential of INRs beyond these domains, this survey aims to provide a comprehensive overview of INR models in the field of medical imaging. In medical settings, numerous challenging and ill-posed problems exist, making INRs an attractive solution. The survey explores the application of INRs in various medical imaging tasks, such as image reconstruction, segmentation, registration, novel view synthesis, and compression. It discusses the advantages and limitations of INRs, highlighting their resolution-agnostic nature, memory efficiency, ability to avoid locality biases, and differentiability, enabling adaptation to different tasks. Furthermore, the survey addresses the challenges and considerations specific to medical imaging data, such as data availability, computational complexity, and dynamic clinical scene analysis. It also identifies future research directions and opportunities, including integration with multimodal imaging, real-time and interactive systems, and domain adaptation for clinical decision support. To facilitate further exploration and implementation of INRs in medical image analysis, we have provided a compilation of cited studies along with their available open-source implementations on GitHub. Finally, we aim to consistently incorporate the most recent and relevant papers regularly. © 2023, CC BY.

关键词： Medical imaging

DAE-Former: Dual Attention-guided Efficient Transformer for Medical Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Azad, Reza Arimond, René Aghdam, Ehsan Khodapanah Kazerouni, Amirhossein Merhof, Dorit Institute of Imaging and Computer Vision RWTH Aachen University Aachen Germany Department of Electrical Engineering Shahid Beheshti University Tehran Iran School of Electrical Engineering Iran University of Science and Technology Tehran Iran Institute of Image Analysis and Computer Vision Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany

Transformers have recently gained attention in the computer vision domain due to their ability to model long-range dependencies. However, the self-attention mechanism, which is the core part of the Transformer model, usually suffers from quadratic computational complexity with respect to the number of tokens. Many architectures attempt to reduce model complexity by limiting the self-attention mechanism to local regions or by redesigning the tokenization process. In this paper, we propose DAE-Former, a novel method that seeks to provide an alternative perspective by efficiently designing the self-attention mechanism. More specifically, we reformulate the self-attention mechanism to capture both spatial and channel relations across the whole feature dimension while staying computationally efficient. Furthermore, we redesign the skip connection path by including the cross-attention module to ensure the feature reusability and enhance the localization power. Our method outperforms state-of-the-art methods on multi-organ cardiac and skin lesion segmentation datasets without requiring pre-training weights. The code is publicly available at GitHub. © 2022, CC BY.

关键词： Reusability

Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Runfa Wang, Ling Du, Yu Xue, Tianrui Sun, Fuchun Zhang, Jianwei Huang, Wenbing Dept. of Comp. Sci. & Tech. Institute for AI BNRist Center Tsinghua University China Dept. of Info. Eng. Xi'an Research Institute of High-Tech China School of Elec. Eng. Naval University of Engineering China College of Arts & Sci. New York Unviersity United States THU-Bosch JCML Center China TAMS Dept. of Informatics University of Hamburg Germany Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China

Learning policies for multi-entity systems in 3D environments is far more complicated against single-entity scenarios, due to the exponential expansion of the global state space as the number of entities increases. One potential solution of alleviating the exponential complexity is dividing the global space into independent local views that are invariant to transformations including translations and rotations. To this end, this paper proposes Subequivariant Hierarchical Neural Networks (SHNN) to facilitate multi-entity policy learning. In particular, SHNN first dynamically decouples the global space into local entity-level graphs via task assignment. Second, it leverages subequivariant message passing over the local entity-level graphs to devise local reference frames, remarkably compressing the representation redundancy, particularly in gravity-affected environments. Furthermore, to overcome the limitations of existing benchmarks in capturing the subtleties of multi-entity systems under the Euclidean symmetry, we propose the Multi-entity Benchmark (MEBEN), a new suite of environments tailored for exploring a wide range of multi-entity reinforcement learning. Extensive experiments demonstrate significant advancements of SHNN on the proposed benchmarks compared to existing methods. Comprehensive ablations are conducted to verify the indispensability of task assignment and subequivariance. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Self-Correcting Robot Manipulation via Gaussian-Splatted Foresight 39

学校读者我要写书评

暂无评论

Self-Correcting Robot Manipulation via Gaussian-Splatted For...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Pan, Shaohui Xu, Yong Xu, Ruotao Zhou, Zihan Wu, Si Yu, Zhuliang School of Computer Science and Engineering South China University of Technology Guangzhou510006 China Guangzhou510000 China Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis Guangzhou510000 China Peng Cheng Laboratory of Shenzhen Shenzhen518120 China Key Laboratory of Large-Model Embodied-Intelligent Humanoid Robot 510000 China School of College of Mathematics and Informatics South China Agricultural University Guangzhou510640 China Shien-Ming Wu School of Intelligent Engineering South China University of Technology Guangzhou510006 China School of Automation Science and Engineering South China University of Technology Guangzhou510006 China

ISBN: (纸本)157735897X

Language-conditioned robotic manipulation in unstructured environments presents significant challenges for intelligent robotic systems. However, due to partial observation or imprecise action prediction, failure may be unavoidable for learned policies. Moreover, operational failures can lead to the robotic arm entering an untrained state, potentially causing destructive results. Consequently, the ability to detect and self-correct failures is crucial for the development of practical robotic systems. To address this challenge, we propose a foresight-driven failure detection and self-correction module for robot manipulation. By leveraging 3D Gaussian Splatting, we represent the current scene with multiple Gaussians. Subsequently, we train a prediction network to forecast the Gaussian representation of future scenes conditioned on planned actions. Failure is detected when the predicted future significantly deviates from the real observation after action execution. In such cases, the end-effector rolls back to the previous action to avoid an untrained state. Integrating this approach with the PerAct framework, we develop a self-correcting robot manipulation policy. Evaluations on ten RL-Bench tasks with 166 variations demonstrate the superior performance of the proposed method, which outperforms state-of-the-art methods by 12.0% success rate on average. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Intelligent robots

Improved Prediction Of Ligand-Protein Binding Affinities By Meta-Modeling

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lee, Ho-Joon Emani, Prashant S. Gerstein, Mark B. Dept. of Genetics and Yale University New HavenCT06510 United States Yale Center for Genome Analysis Yale University New HavenCT06510 United States Dept. of Molecular Biophysics & Biochemistry Yale University New HavenCT06520 United States Program in Computational Biology & Bioinformatics Yale University New HavenCT06520 United States Dept. of Computer Science Yale University New HavenCT06520 United States Dept. of Statistics & Data Science Yale University New HavenCT06520 United States Dept. of Biomedical Informatics & Data Science Yale University New HavenCT06520 United States

The accurate screening of candidate drug ligands against target proteins through computational approaches is of prime interest to drug development efforts. Such virtual screening depends in part on methods to predict the binding affinity between ligands and proteins. Many computational models for binding affinity prediction have been developed, but with varying results across targets. Given that ensembling or meta-modeling approaches have shown great promise in reducing model-specific biases, we develop a framework to integrate published force-field-based empirical docking and sequence-based deep learning models. In building this framework, we evaluate many combinations of individual base models, training databases, and several meta-modeling approaches. We show that many of our meta-models significantly improve affinity predictions over base models. Our best meta-models achieve comparable performance to state-of-the-art deep learning tools exclusively based on 3D structures, while allowing for improved database scalability and flexibility through the explicit inclusion of features such as physicochemical properties or molecular descriptors. We further demonstrate improved generalization capability by our models using a large-scale benchmark of affinity prediction as well as a virtual screening application benchmark. Overall, we demonstrate that diverse modeling approaches can be ensembled together to gain meaningful improvement in binding affinity prediction. © 2023, CC BY-NC-SA.

关键词： Prediction models

Performance of multimodal prediction models for intracerebral hemorrhage outcomes using real-world data

学校读者我要写书评

暂无评论

International Journal of Medical informatics 2025年 202卷 105989-105989页

作者： Matsumoto, Koutarou Suzuki, Masahiro Ishihara, Kazuaki Tokunaga, Koki Matsuda, Katsuhiko Chen, Jenhui Yamashiro, Shigeo Soejima, Hidehisa Nakashima, Naoki Kamouchi, Masahiro Department of Health Care Administration and Management of Medical Sciences Kyushu University Fukuoka Japan Graduate Degree Program of Applied Data Sciences Sophia University Tokyo Japan Department of Computer Science and Information Engineering Chang Gung University Taoyuan Taiwan Department of Pharmacy Saiseikai Kumamoto Hospital Kumamoto Japan Department of Radiology Saiseikai Kumamoto Hospital Kumamoto Japan Division of Neurosurgery Saiseikai Kumamoto Hospital Kumamoto Japan Institute for Medical Information Research and Analysis Saiseikai Kumamoto Hospital Kumamoto Japan Medical Information Center Kyushu University Hospital Fukuoka Japan Department of Medical Informatics of Medical Sciences Kyushu University Fukuoka Japan Center for Cohort Studies of Medical Sciences Kyushu University Fukuoka Japan

Background: We aimed to develop and validate multimodal models integrating computed tomography (CT) images, text and tabular clinical data to predict poor functional outcomes and in-hospital mortality in patients with intracerebral hemorrhage (ICH). These models were designed to assist non-specialists in emergency settings with limited access to stroke specialists. Methods: A retrospective analysis of 527 patients with ICH admitted to a Japanese tertiary hospital between April 2019 and February 2022 was conducted. Deep learning techniques were used to extract features from three-dimensional CT images and unstructured data, which were then combined with tabular data to develop an L1-regularized logistic regression model to predict poor functional outcomes (modified Rankin scale score 3–6) and in-hospital mortality. The model's performance was evaluated by assessing discrimination metrics, calibration plots, and decision curve analysis (DCA) using temporal validation data. Results: The multimodal model utilizing both imaging and text data, such as medical interviews, exhibited the highest performance in predicting poor functional outcomes. In contrast, the model that combined imaging with tabular data, including physiological and laboratory results, demonstrated the best predictive performance for in-hospital mortality. These models exhibited high discriminative performance, with areas under the receiver operating curve (AUROCs) of 0.86 (95% CI: 0.79–0.92) and 0.91 (95% CI: 0.84–0.96) for poor functional outcomes and in-hospital mortality, respectively. Calibration was satisfactory for predicting poor functional outcomes, but requires refinement for mortality prediction. The models performed similar to or better than conventional risk scores, and DCA curves supported their clinical utility. Conclusion: Multimodal prediction models have the potential to aid non-specialists in making informed decisions regarding ICH cases in emergency departments as part of clinical dec

关键词： Logistic regression